Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 22110
    Prev
    Next
    INDEX
    Explanations

    social media platforms, specifically focusing on Pinterest

    oai_token-act-pair · gpt-3.5-turbo

    references to the social media platform Pinterest

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    otech
    -0.70
     scrimmage
    -0.67
    thro
    -0.66
    zie
    -0.65
    ilic
    -0.64
     frag
    -0.64
    atics
    -0.63
     roomm
    -0.61
    lie
    -0.58
     unborn
    -0.58
    POSITIVE LOGITS
     Pinterest
    1.09
    annels
    0.81
    sylv
    0.76
     PHOTO
    0.75
     Flavoring
    0.75
     Thumbnails
    0.74
    atchewan
    0.74
    psey
    0.73
     Sketch
    0.72
    LinkedIn
    0.72
    Activations Density 0.005%

    No Known Activations